Skip to content

Commit a8a62e7

Browse files
authored
Add news to ROCm blog (#326)
Added 'type' field to blog post metadata.
1 parent c37a1e5 commit a8a62e7

1 file changed

Lines changed: 1 addition & 0 deletions

File tree

blog/2026-03-17-rocm-miles-rl-amd.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,7 @@ title: "ROCm Support for Miles: Large-Scale RL Post-Training on AMD Instinct™
33
author: "AMD & Miles Team"
44
date: "March 17, 2026"
55
previewImg: /images/blog/rocm_miles_rl/fig_1.png
6+
type: news
67
---
78

89
Reinforcement learning (RL) has rapidly become a core stage of modern foundation-model development. While large-scale pretraining remains essential, today's most capable models rely heavily on post-training techniques to improve reasoning, tool use, and multi-turn interaction. These workflows depend on scalable reinforcement learning infrastructure capable of running across multi-node GPU clusters.

0 commit comments

Comments
 (0)